Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating negation or the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ɵ
    -0.17
    atern
    -0.17
    ccak
    -0.16
    \Mapping
    -0.15
    igan
    -0.15
    aily
    -0.14
    apı
    -0.14
    geois
    -0.14
    embros
    -0.14
    weis
    -0.13
    POSITIVE LOGITS
    owell
    0.19
     fl
    0.15
    /do
    0.14
     být
    0.14
     Pins
    0.14
     flo
    0.14
    kest
    0.13
    itia
    0.13
     mic
    0.13
    ãĥ¼ãĤ¹ãĥĪ
    0.13
    Act Density 0.131%

    No Known Activations